On Wed, Sep 26, 2018 at 01:13:45PM -0700, Steve Wise wrote:
> Add support for new LINK messages to allow adding and deleting rdma
> interfaces. This will be used initially for soft rdma drivers which
> instantiate device instances dynamically by the admin specifying a netdev
> device to use. The rdma_rxe module will be the first user of these
> messages.
>
> The design is modeled after RTNL_NEWLINK/DELLINK: rdma drivers
> register with the rdma core if they provide link add/delete functions.
> Each driver registers with a unique "type" string, that is used to
> dispatch messages coming from user space. A new RDMA_NLDEV_ATTR is
> defined for the "type" string. User mode will pass 3 attributes in a
> NEWLINK message: RDMA_NLDEV_ATTR_IBDEV_NAME for the desired rdma device
> name to be created, RDMA_NLDEV_ATTR_LINK_TYPE for the "type" of link
> being added, and RDMA_NLDEV_ATTR_NDEV_NAME for the net_device interface
> to use for this link. The DELLINK message will contain the IBDEV_NAME
> and LINK_TYPE attributes.
>
> Signed-off-by: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>
> drivers/infiniband/core/nldev.c | 128 +++++++++++++++++++++++++++++++++++++++
> include/rdma/rdma_netlink.h | 13 ++++
> include/uapi/rdma/rdma_netlink.h | 9 ++-
> 3 files changed, 149 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
> index e841725a0ee0..a5982cda6956 100644
> +++ b/drivers/infiniband/core/nldev.c
> @@ -33,6 +33,7 @@
> #include <linux/module.h>
> #include <linux/pid.h>
> #include <linux/pid_namespace.h>
> +#include <linux/mutex.h>
> #include <net/netlink.h>
> #include <rdma/rdma_cm.h>
> #include <rdma/rdma_netlink.h>
> @@ -107,6 +108,8 @@
> [RDMA_NLDEV_ATTR_DRIVER_U32] = { .type = NLA_U32 },
> [RDMA_NLDEV_ATTR_DRIVER_S64] = { .type = NLA_S64 },
> [RDMA_NLDEV_ATTR_DRIVER_U64] = { .type = NLA_U64 },
> + [RDMA_NLDEV_ATTR_LINK_TYPE] = { .type = NLA_NUL_STRING,
> + .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN },
> };
>
> static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
> @@ -1102,6 +1105,123 @@ static int nldev_res_get_pd_dumpit(struct sk_buff *skb,
> return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_PD);
> }
>
> +static LIST_HEAD(link_ops);
> +static DEFINE_MUTEX(link_ops_mutex);
> +
> +static const struct rdma_link_ops *link_ops_get(const char *type)
> +{
> + const struct rdma_link_ops *ops;
> +
> + mutex_lock(&link_ops_mutex);
> + list_for_each_entry(ops, &link_ops, list) {
> + if (!strcmp(ops->type, type))
> + goto out;
> + }
> + ops = NULL;
> +out:
> + mutex_unlock(&link_ops_mutex);
> + return ops;
> +}
> +
> +void rdma_link_register(struct rdma_link_ops *ops)
> +{
> + if (link_ops_get(ops->type)) {
> + WARN_ONCE("Duplicate rdma_link_ops! %s\n", ops->type);
> + return;
> + }
> + mutex_lock(&link_ops_mutex);
> + list_add(&ops->list, &link_ops);
> + mutex_unlock(&link_ops_mutex);
> +}
> +EXPORT_SYMBOL(rdma_link_register);
> +
> +void rdma_link_unregister(struct rdma_link_ops *ops)
> +{
> + mutex_lock(&link_ops_mutex);
> + list_del(&ops->list);
> + mutex_unlock(&link_ops_mutex);
> +}
> +EXPORT_SYMBOL(rdma_link_unregister);
> +
> +static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
> + struct netlink_ext_ack *extack)
> +{
> + struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
> + char ibdev_name[IB_DEVICE_NAME_MAX];
> + const struct rdma_link_ops *ops;
> + char ndev_name[IFNAMSIZ];
> + char type[IFNAMSIZ];
> + int err;
> +
> +#ifdef CONFIG_MODULES
> +replay:
> +#endif
> + err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
> + nldev_policy, extack);
> + if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
> + !tb[RDMA_NLDEV_ATTR_LINK_TYPE] || !tb[RDMA_NLDEV_ATTR_NDEV_NAME]) {
> + err = -EINVAL;
> + goto err_out;
> + }
> +
> + nla_strlcpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
> + sizeof(ibdev_name));
> + nla_strlcpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
> + nla_strlcpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME],
> + sizeof(ndev_name));
These nla_strlcpy's should fail the syscall if the name is longer than
our buffer, not truncate and wrongly continue.
> + pr_debug("ibdev_name |%s| type |%s| ndev_name |%s|\n", ibdev_name,
> + type, ndev_name);
> +
> + ops = link_ops_get(type);
> + if (!ops) {
> +#ifdef CONFIG_MODULES
> + request_module("rdma-link-%s", type);
> + ops = link_ops_get(type);
> + if (ops)
> + goto replay;
> +#endif
> + err = -ENODEV;
> + goto err_out;
> + }
> +
> + err = ops->newlink(ibdev_name, ndev_name);
Need to check there is no % in the ibdev_name or ib_register will do
something wrong
> diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
> index c369703fcd69..9bb8e1351a30 100644
> +++ b/include/rdma/rdma_netlink.h
> @@ -99,4 +99,17 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
> * Returns 0 on success or a negative for no listeners.
> */
> int rdma_nl_chk_listeners(unsigned int group);
> +
> +struct rdma_link_ops {
> + struct list_head list;
> + const char *type;
> + int (*newlink)(char *ibdev_name, char *ndev_name);
> + int (*dellink)(char *ibdev_name);
const char *
Jason
